The 1st place winner of the 4th Low-Power Computer Vision Challenge

We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. We propose a Once-for-All Network (OFA, ICLR’2020) that supports diverse architectural settings by decoupling model training and architecture search. We can quickly get a specialized sub-network by selecting from the OFA network without additional training. We also propose a novel progressive shrinking algorithm, a generalized pruning method that reduces the model size across many more dimensions than pruning (depth, width, kernel size, and resolution), which can obtain a surprisingly large number of sub-networks (> 1019) that can fit different latency constraints. On edge devices, OFA consistently outperforms SOTA NAS methods (up to 4.0% ImageNet top1 accuracy improvement over MobileNetV3, or same accuracy but 1.5x faster than MobileNetV3, 2.6x faster than EfficientNet w.r.t measured latency) while reducing many orders of magnitude GPU hours and CO2 emission. In particular, OFA achieves a new SOTA 80.0% ImageNet top1 accuracy under 600M MACs. OFA is the winning solution for 4th Low Power Computer Vision Challenge, both classification track and detection track. Code and 50 pre-trained models on CPU/GPU/DSP/mobile CPU/mobile GPU (for different device & different latency constraints) are released at

We participate in the 4th On-device Visual Intelligence Competition (OVIC) of Low-Power Computer Vision Challenge (LPCVC) using the Once-for-all Network algorithm. The challenge competes for the best accuracy given latency constraint deploying neural networks on mobile phones (i.e. Google Pixel 2). Our team won 1st place in both tracks classification track and detection track. The code is released at